Go to Article >>

Randomization is a practice used to assign subjects to experimental groups in a research study.

For example, consider a fictitious research study meant to compare the effectiveness of a new drugs for reducing blood pressure. The researchers will recruit a number of participants or subjects, making every attempt to make sure the participants are as similar as possible (similar medical histories, similar pre-existing blood pressure, etc.). Then the researchers will randomly assign each subject to either the experimental or the control group -- for example, by flipping a coin. Subjects in the experimental group will take the new drug for a number of weeks; subjects in the control group will take an inactive compound or placebo for comparison. At the end of some period, the researchers will then test blood pressure in all subjects, to see if those subjects who took the new drug have lower blood pressure, on average, than subjects who took the placebo. If so, this would imply that the new drug is effective for lowering blood pressure.

The practice of randomization is one way to help make sure that there are no preexisting differences between the subjects in each group. That way, any differences in blood pressure at the end of the study can reasonably be attributed to the effects of the drug being evaluated -- and not to some inadvertent bias on the part of the researcher for assigning people to one group or the other. Well-designed research studies, particularly clinical trials of new drugs, usually employ randomization, placebo controls and double-blind techniques.

Further Reading: "Putting Ginkgo to the Test"